DeSPU: Privacy-Compliant Decentralized Sparse Personalized Federated Unlearning for Edge Intelligence-Enabled IoT Networks
DeSPU is proposed, a decentralized sparse personalized federated unlearning framework under a practical deletion-window protocol that estimates a target-class direction with a lightweight dual-model mechanism, applies semantic-layer adaptive linear unlearning to suppress target knowledge, and performs topology-aware lo...